Update app.py

app.py

@@ -14,17 +14,17 @@ def list_files_tree(directory, indent=""):
             next_indent = indent + ("    " if i == len(items) - 1 else "│   ")
             list_files_tree(item_path, next_indent)
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+pipeline = None
 
-repo_id = "None1145/ChatGLM3-6B-Theresa-GGML"
-filename = "ChatGLM3-6B-Theresa-GGML-Q4_0.bin"
-hf_hub_download(repo_id=repo_id, filename=filename, local_dir=f"./Models/{repo_id}")
-model = f"./Models/{repo_id}/{filename}"
-max_length = 8192
-pipeline = chatglm_cpp.Pipeline(model, max_length=max_length)
+def load(repo_id, filename):
+    global pipeline
+    local_dir = f"./Models/{repo_id}"
+    hf_hub_download(repo_id=repo_id, filename=filename, local_dir=local_dir)
+    model = os.path.join(local_dir, filename)
+    max_length = 8192
+    pipeline = chatglm_cpp.Pipeline(model, max_length=max_length)
+    return f"Model {filename} from {repo_id} loaded successfully."
+load("None1145/ChatGLM3-6B-Theresa-GGML", "ChatGLM3-6B-Theresa-GGML-Q4_0.bin")
 
 messages = []
 
@@ -38,11 +38,15 @@ def respond(
 ):
     global messages
 
+    if pipeline is None:
+        yield "Error: No model loaded. Please load a model first."
+        return
+
     response = ""
     yield response
     
     generation_kwargs = dict(
-        max_length=max_length,
+        max_length=8192,
         max_context_length=max_tokens,
         do_sample=temperature > 0,
         top_k=0,
@@ -55,43 +59,38 @@ def respond(
     if messages == []:
         messages = [chatglm_cpp.ChatMessage(role="system", content=system_message)]
 
-    # for val in history:
-    #     if val[0]:
-    #         messages.append(chatglm_cpp.ChatMessage(role="user", content=val[0]))
-    #     if val[1]:
-    #         messages.append(chatglm_cpp.ChatMessage(role="assistant", content=val[0]))
-
     messages.append(chatglm_cpp.ChatMessage(role="user", content=message))
     
-    chunks = []
-
     for chunk in pipeline.chat(messages, **generation_kwargs):
         response += chunk.content
-        chunks.append(chunk)
         yield response
         
     messages.append(chatglm_cpp.ChatMessage(role="assistant", content=response))
 
+with gr.Blocks() as chat:
+    with gr.Row():
+        repo_id_input = gr.Textbox(label="Repo ID", value="None1145/ChatGLM3-6B-Theresa-GGML")
+        filename_input = gr.Textbox(label="Filename", value="ChatGLM3-6B-Theresa-GGML-Q4_0.bin")
+        load_button = gr.Button("Load Model")
+    
+    load_status = gr.Textbox(label="Load Status", interactive=False)
+    load_button.click(load, inputs=[repo_id_input, filename_input], outputs=load_status)
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
+    chat_interface = gr.ChatInterface(
+        respond,
+        additional_inputs=[
+            gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+            gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+            gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+            gr.Slider(
+                minimum=0.1,
+                maximum=1.0,
+                value=0.95,
+                step=0.05,
+                label="Top-p (nucleus sampling)",
+            ),
+        ],
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    chat.launch()